Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add MuJoCo Robotics Envs HER+TQC trained agents #71

Merged
merged 5 commits into from Mar 15, 2021
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
5 changes: 4 additions & 1 deletion benchmark.md
Expand Up @@ -62,6 +62,10 @@ and also allow users to have access to pretrained agents.*
|dqn |RoadRunnerNoFrameskip-v4 | 40396.350| 7069.131|10M | 603257| 137|
|dqn |SeaquestNoFrameskip-v4 | 2000.290| 606.644|10M | 599505| 69|
|dqn |SpaceInvadersNoFrameskip-v4| 622.742| 201.564|10M | 604311| 155|
|her |FetchPickAndPlace-v1 | -8.921| 6.509|1M | 150000| 3000|
|her |FetchPush-v1 | -10.526| 8.916|1M | 150000| 3000|
|her |FetchReach-v1 | -1.677| 1.069|20k | 150000| 3000|
|her |FetchSlide-v1 | -23.162| 10.625|2M | 150000| 3000|
|her |parking-v0 | -6.970| 2.970|200k | 149980| 7106|
|ppo |Acrobot-v1 | -73.506| 18.201|1M | 149979| 2013|
|ppo |AntBulletEnv-v0 | 2865.922| 56.468|2M | 150000| 150|
Expand Down Expand Up @@ -91,7 +95,6 @@ and also allow users to have access to pretrained agents.*
|qrdqn|BeamRiderNoFrameskip-v4 | 17122.941| 10769.997|10M | 596483| 17|
|qrdqn|BreakoutNoFrameskip-v4 | 393.600| 79.828|10M | 579711| 40|
|qrdqn|CartPole-v1 | 500.000| 0.000|50k | 150000| 300|
|qrdqn|EnduroNoFrameskip-v4 | 3231.200| 1311.801|10M | 585728| 5|
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it looks like I forgot to push the benchmark log of that one... (I will do that soon)
Please do the same for the robotics envs (files are in logs/benchmark/, you may need git add -f for that)

|qrdqn|LunarLander-v2 | 70.236| 225.491|100k | 149957| 522|
|qrdqn|MountainCar-v0 | -106.042| 15.536|120k | 149943| 1414|
|qrdqn|PongNoFrameskip-v4 | 20.492| 0.687|10M | 597443| 63|
Expand Down
2 changes: 1 addition & 1 deletion hyperparams/her.yml
Expand Up @@ -52,7 +52,7 @@ FetchPush-v1:
FetchSlide-v1:
env_wrapper:
- sb3_contrib.common.wrappers.TimeFeatureWrapper
n_timesteps: !!float 1e6
n_timesteps: !!float 2.5e6
policy: 'MlpPolicy'
model_class: 'tqc'
n_sampled_goal: 4
Expand Down